Feedforward neural network design with tridiagonal symmetry constraints

TitleFeedforward neural network design with tridiagonal symmetry constraints
Publication TypeJournal Article
Year of Publication2000
AuthorsDumitras, A., and F. Kossentini
JournalSignal Processing, IEEE Transactions on
Pagination1446 -1454
Date Publishedmay.
Keywordscomplexity, computational complexity, FANN design, feedforward neural nets, feedforward neural network design, input-hidden weight matrix, matrix algebra, nonlinear regression problem, performance, pruning algorithm, reflection transform, statistical analysis, transforms, tridiagonal symmetry constraints

This paper introduces a pruning algorithm with tridiagonal symmetry constraints for feedforward neural network (FANN) design. The algorithm uses a reflection transform applied to the input-hidden weight matrix in order to reduce it to its tridiagonal form. The designed FANN structures obtained by applying the proposed algorithm are compact and symmetrical. Therefore, they are well suited for efficient hardware and software implementations. Moreover, the number of the FANN parameters is reduced without a significant loss in performance. We illustrate the complexity and performance of the proposed algorithm by applying it as a solution to a nonlinear regression problem. We also compare the results of our proposed algorithm with those of the optimal brain damage algorithm


a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2021 The University of British Columbia